{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DST6VGS7VGZFCKDRSQZDEDA2MJ","short_pith_number":"pith:DST6VGS7","schema_version":"1.0","canonical_sha256":"1ca7ea9a5fa9b25128719432320c1a6272ac671c8b701ef87db4df63983f00e2","source":{"kind":"arxiv","id":"2606.02079","version":1},"attestation_state":"computed","paper":{"title":"FACT: A Simple and Efficient Framework for Active Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Minjie Ren, Qingjie Liu, Wenshuai Xu, You Song, Yuzhuo Cui, Zhenghui Hu","submitted_at":"2026-06-01T11:08:31Z","abstract_excerpt":"The main goal of active finetuning is to improve a pretrained model's performance on a specific task or domain by finetuning it with carefully selected informative or challenging data. Previous research has predominantly focused on the active aspect (i.e., data selection) while uniformly employing full finetuning for model adaptation, which inevitably distorts pretrained features due to distribution shift. This issue becomes particularly pronounced when the model size is large relative to the finetuning data quantity, leading to heightened overfitting risks. To address this critical gap, we fo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T11:08:31Z","cross_cats_sorted":[],"title_canon_sha256":"5743b0dac2f58adfbc083a2be6243ab99a62ca465b0432f22717db1a72aaaf2d","abstract_canon_sha256":"416adbbc4fe81e0c47031e327c2d8e9b72b01687fa07c3f786310d4bcaca9c6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:05.469074Z","signature_b64":"aM0yiCb3sy+h5v/DXGZ8S5jIPdNhOwBtJZ/VE3dmf1yW7YNFfrNNJb//i3O58TmfcCl7co2ETpPgrGK+UqPOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca7ea9a5fa9b25128719432320c1a6272ac671c8b701ef87db4df63983f00e2","last_reissued_at":"2026-06-02T02:05:05.468527Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:05.468527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FACT: A Simple and Efficient Framework for Active Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Minjie Ren, Qingjie Liu, Wenshuai Xu, You Song, Yuzhuo Cui, Zhenghui Hu","submitted_at":"2026-06-01T11:08:31Z","abstract_excerpt":"The main goal of active finetuning is to improve a pretrained model's performance on a specific task or domain by finetuning it with carefully selected informative or challenging data. Previous research has predominantly focused on the active aspect (i.e., data selection) while uniformly employing full finetuning for model adaptation, which inevitably distorts pretrained features due to distribution shift. This issue becomes particularly pronounced when the model size is large relative to the finetuning data quantity, leading to heightened overfitting risks. To address this critical gap, we fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02079","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.02079/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02079","created_at":"2026-06-02T02:05:05.468593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02079v1","created_at":"2026-06-02T02:05:05.468593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02079","created_at":"2026-06-02T02:05:05.468593+00:00"},{"alias_kind":"pith_short_12","alias_value":"DST6VGS7VGZF","created_at":"2026-06-02T02:05:05.468593+00:00"},{"alias_kind":"pith_short_16","alias_value":"DST6VGS7VGZFCKDR","created_at":"2026-06-02T02:05:05.468593+00:00"},{"alias_kind":"pith_short_8","alias_value":"DST6VGS7","created_at":"2026-06-02T02:05:05.468593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ","json":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ.json","graph_json":"https://pith.science/api/pith-number/DST6VGS7VGZFCKDRSQZDEDA2MJ/graph.json","events_json":"https://pith.science/api/pith-number/DST6VGS7VGZFCKDRSQZDEDA2MJ/events.json","paper":"https://pith.science/paper/DST6VGS7"},"agent_actions":{"view_html":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ","download_json":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ.json","view_paper":"https://pith.science/paper/DST6VGS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02079&json=true","fetch_graph":"https://pith.science/api/pith-number/DST6VGS7VGZFCKDRSQZDEDA2MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DST6VGS7VGZFCKDRSQZDEDA2MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ/action/storage_attestation","attest_author":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ/action/author_attestation","sign_citation":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ/action/citation_signature","submit_replication":"https://pith.science/pith/DST6VGS7VGZFCKDRSQZDEDA2MJ/action/replication_record"}},"created_at":"2026-06-02T02:05:05.468593+00:00","updated_at":"2026-06-02T02:05:05.468593+00:00"}